I have written gemma3 inference in pure C
Posted by robitec97 2 days ago
Comments
Comment by austinvhuang 3 hours ago
There's such a massive performance differential vs. SIMD though that I learned to appreciate SIMD (via highway) as one sweet spot of low-dependency portability that sits between C loops and the messy world of GPUs + their fat tree of dependencies.
If anyone want to learn the basics - whip out your favorite LLM pair programmer and ask it to help you study the kernels in the ops/ library of gemma.cpp:
Comment by janwas 3 hours ago
Comment by w4yai 3 hours ago
Did we need any proof of that ?
Comment by jdefr89 3 hours ago
Comment by jasonjmcghee 3 hours ago
Comment by christianqchung 1 hour ago
Comment by skybrian 3 hours ago
Comment by kgeist 3 hours ago
Comment by tolerance 3 hours ago
I know very little about AI but these are things that come to mind here for me.
Comment by yorwba 3 hours ago
Comment by tolerance 3 hours ago
Comment by behnamoh 3 hours ago
Comment by uncognic 3 hours ago
Comment by NitpickLawyer 3 hours ago
Umm, we do. It's still one of the best for eu countries support / help chatbot style. It's got good (best?) multilingual support ootb, it's very "safe" (won't swear, won't display chinese characters, etc) and it's pretty fast.
Comment by gunalx 2 hours ago
Comment by behnamoh 2 hours ago
Comment by data-ottawa 2 hours ago